# Learning to Deceive in Multi-Agent Hidden Role Games

arXiv: https://arxiv.org/abs/2209.01551 · HTML: https://mlsanity.com/paper/2209.01551/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2022.

## Built on by (most cited first, 5 of 5)

- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Deception Analysis with Artificial Intelligence: An Interdisciplinary Perspective](https://mlsanity.com/paper/2406.05724/) (2024)
- [Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies](https://mlsanity.com/paper/2512.16167/) (2025)
- [A Survey on Hypergame Theory: Modelling Misaligned Perceptions and Nested Beliefs for Multi-Agent Systems](https://mlsanity.com/paper/2507.19593/) (2025)
- [Differentiable Belief-based Opponent Shaping](https://mlsanity.com/paper/2605.29042/) (2026)

## Abstract (arXiv)

Deception is prevalent in human social settings. However, studies into the effect of deception on reinforcement learning algorithms have been limited to simplistic settings, restricting their applicability to complex real-world problems. This paper addresses this by introducing a new mixed competitive-cooperative multi-agent reinforcement learning (MARL) environment inspired by popular role-based deception games such as Werewolf, Avalon, and Among Us. The environment's unique challenge lies in the necessity to cooperate with other agents despite not knowing if they are friend or foe. Furthermore, we introduce a model of deception, which we call Bayesian belief manipulation (BBM) and demonstrate its effectiveness at deceiving other agents in this environment while also increasing the deceiving agent's performance.